Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ]).
    -0.07
     equalTo
    -0.06
     deltas
    -0.06
     detention
    -0.06
    VAL
    -0.06
    dT
    -0.06
     Kant
    -0.06
     antagonist
    -0.06
     Hale
    -0.06
     fairy
    -0.06
    POSITIVE LOGITS
     intric
    0.07
    rvine
    0.07
    UTO
    0.06
     زند
    0.06
    _bold
    0.06
    τήσεις
    0.06
     dévelop
    0.06
     imaginative
    0.06
    ỗ
    0.06
     Unter
    0.06
    Act Density 0.006%

    No Known Activations